Home › Code › cosine_sim

cosine_sim

Syntologyentry name in harvested coderead from the graph 2026-09-24

cosine_sim appears in the code Syntology harvested for 34 papers, as 20 distinct code bodies found in 38 places (a place is one code body under one paper). At least one of them ran in 21 of the papers; 5 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named cosine_sim do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 8 of the 20 distinct code bodies named cosine_sim; 12 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
0ran · fixture could not drive it
5ran
12unverified
5fingerprinted

Licence is a property of each copy, so it is counted per place: 7 of the 38 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

34 papers shown of 34, newest first; 38 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 3 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
ISM: Self-Improving Strategy Memory for Continual Mathematical Reasoning added by Syntology 2026-06 (from id) pdx97/ISM/baseline_rag_examples.py 29d3697dff1ffa09 ran fingerprinted MIT (permissive)
Can Agents Read the Room? Benchmarking Visual Social Intelligence in Multimodal Simulation added by Syntology 2026-06 (from id) JunsWan/AgentViSS/data_pipline/src/base_scenarios/base_json_builder.py de67ec8e60be1060 ran fingerprinted no licence file found · pointer only
Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems added by Syntology 2026-03 (from id) scthornton/semantic-chameleon/experiments/exp1_fever_large_scale.py 35888a241a6e7334 unverified licence not identified · pointer only
Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems added by Syntology 2026-03 (from id) scthornton/semantic-chameleon/experiments/exp3_joint_hybrid_attack.py 2651ba6348e96208 unverified licence not identified · pointer only
Optimal Brain Apoptosis 25 Feb 2025 NEU-REAL/OBA/modules/models.py 540fe9d9ed2115e9 unverified MIT (permissive)
MVC-VPR: Mutual Learning of Viewpoint Classification and Visual Place Recognition 12 Dec 2024 Gucci233/MutualVPR/cosface_loss.py d7ebec9a9c0c9b14 unverified no licence file found · pointer only
AnyPattern: Towards In-context Image Copy Detection 21 Apr 2024 wangwenhao0716/anypattern/Train/dg/layer.py 55b7eacdfa96a1c5 ran MIT (permissive)
AnyPattern: Towards In-context Image Copy Detection 21 Apr 2024 wangwenhao0716/anypattern/Train/dg/models_gem_waveblock_balance_cos/metric.py 475146601a2a3bf5 ran MIT (permissive)
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey 8 Feb 2024 zjukg/snag/SNAG_MMEA/model/EVA_tools.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
Cross-modal Active Complementary Learning with Self-refining Correspondence 26 Oct 2023 QinYang79/CRCL/CRCL_NeurIPS23/model/SGRAF.py 3a3ba65d84f3eeff ran no licence file found · pointer only
Improving equilibrium propagation without weight symmetry through Jacobian homeostasis 5 Sep 2023 laborieux-axel/generalized-holo-ep/models/dyn.py 0012fbb455bb7410 ran · violated contract fingerprinted MIT (permissive)
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition 21 Aug 2023 gmberton/eigenplaces/cosface_loss.py d7ebec9a9c0c9b14 unverified MIT (permissive)
Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment 30 Jul 2023 zjukg/umaea/UMAEA/model/UMAEA_loss.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training 15 Jun 2023 lcfractal/tgdt/models/loss.py 7f3908ad08980104 unverified MIT (permissive)
Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training 15 Jun 2023 lcfractal/tgdt/utils.py f2e17288ada8cf89 unverified MIT (permissive)
Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring 26 May 2023 doheejin/protact/models/ProTACT.py 32688baeee05d994 unverified BSD-3-Clause (permissive)
A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension 5 May 2023 callsys/textvr/model/loss.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid 29 Dec 2022 zjukg/MEAformer/model/MEAformer_loss.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
Multi-modal Contrastive Representation Learning for Entity Alignment 2 Sep 2022 lzxlin/mclea/src/models.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features 14 Jun 2022 flipz357/S3BERT/src/prediction_helpers.py b7d99c0d0c53c89d unverified MIT (permissive)
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval 1 Apr 2021 m-bain/frozen-in-time/model/loss.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
Universal Representation Learning from Multiple Domains for Few-shot Classification 25 Mar 2021 tmlr-group/mokd/models/model_utils.py 28cc87a06ba68afb unverified MIT (permissive)
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning 1 Nov 2020 gingsi/coot-videotext/coot/loss_fn.py 041513be6fc3b19c unverified Apache-2.0 (permissive)
Visual Pivoting for (Unsupervised) Entity Alignment 28 Sep 2020 cambridgeltl/eva/src/models.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders 12 Aug 2020 mesnico/TERAN/models/loss.py 7f3908ad08980104 unverified Apache-2.0 (permissive)
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders 12 Aug 2020 mesnico/TERAN/utils.py f2e17288ada8cf89 unverified Apache-2.0 (permissive)
Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification 20 Mar 2020 dvornikita/SUR/models/model_utils.py 28cc87a06ba68afb unverified MIT (permissive)
Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning 1 Mar 2020 cshizhe/hgr_v2t/t2vretrieval/models/criterion.py 69d3077d6161e310 unverified MIT (permissive)
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval 12 Sep 2019 ZihaoWang-CV/CAMP_iccv19/model.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Compositional Generalization in Image Captioning 10 Sep 2019 mitjanikolaus/compositional-image-captioning/models/bottom_up_top_down_ranking.py e27049b9e3cf1825 ran · honoured contract fingerprinted licence not identified · pointer only
Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval 11 Jun 2019 yalesong/pvse/loss.py e42286bdac3eb647 unverified MIT (permissive)
LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech 2019-04 (from id) skakouros/bert-prosody/losses.py 55b7eacdfa96a1c5 ran MIT (permissive)
Dual Encoding for Zero-Example Video Retrieval 17 Sep 2018 danieljf24/dual_encoding/loss.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples 27 Jun 2018 ExplorerFreda/VSE-C/VSE_C/model.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives 18 Jul 2017 kadarakos/mulisera/model.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted no licence file found · pointer only
arXiv:aaai_26699 fuenwang/MixFairFace/MixFairFace/CosFace.py 55b7eacdfa96a1c5 ran MIT (permissive)
arXiv:2022.findings-emnlp.24 StanLei52/TQVSR/models/loss.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted MIT (permissive)
arXiv:136960251 silenceFS/LINAS/loss.py 9b0a787b92a87023 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections